Article Contents
Article Contents

# Clustering based polyhedral conic functions algorithm in classification

• In this study, a new algorithm based on polyhedral conic functions (PCFs) is developed to solve multi-class supervised data classification problems. The $k$ PCFs are constructed for each class in order to separate it from the rest of the data set. The $k$-means algorithm is applied to find vertices of PCFs and then a linear programming model is solved to calculate the parameters of each PCF. The separating functions for each class are obtained as a pointwise minimum of the PCFs. A class label is assigned to the test point according to its minimum value over all separating functions. In order to demonstrate the performance of the proposed algorithm, it is applied to solve classification problems in publicly available data sets. The comparative results with some mainstream classifiers are presented.
Mathematics Subject Classification: Primary: 68Q32, 46N10; Secondary: 97R50.

 Citation:

•  [1] A. Astorino and M. Gaudioso, Polyhedral separability through successive LP, Journal of Optimization Theory and Applications, 112 (2002), 265-293.doi: 10.1023/A:1013649822153. [2] A. Astorino, M. Gaudioso and A. Seeger, Conic separation of finite sets. i: The homogeneous case, Journal of Convex Analysis, 21 (2014), 001-028. [3] K. Bache and M. Lichman, UCI machine learning repository, 2013. URL http://archive.ics.uci.edu/ml. [4] A. M. Bagirov, Max-min separability, Optimization Methods and Software, 20 (2005), 277-296.doi: 10.1080/10556780512331318263. [5] A. M. Bagirov and J. Ugon, Supervised data classification via max-min separability, Applied Optimization, 99 (2005), 175-207.doi: 10.1007/0-387-26771-9_6. [6] A. M. Bagirov, M. Ghosh and D. Webb, A derivative-free method for linearly constrained nonsmooth optimization, Journal of Industrial and Management Optimization, 2 (2006), 319-338. [7] A. M. Bagirov, J. Ugon, D. Webb, G. Ozturk and R. Kasimbeyli, A novel piecewise linear classifier based on polyhedral conic and max-min separabilities, TOP, 21 (2013), 3-24. ISSN 1134-5764.doi: 10.1007/s11750-011-0241-5. [8] C. J. C. Burges, A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery, 2 (1998), 121-167. [9] R. N. Gasimov and G. Ozturk, Separation via polihedral conic functions, Optimization Methods and Software, 21 (2006), 527-540.doi: 10.1080/10556780600723252. [10] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann and I. H. Witten, The weka data mining software: An update, SIGKDD Explorations, 11 (2009), 10-18. ISSN 1931-0145.doi: 10.1145/1656274.1656278. [11] R. Kasimbeyli, Radial epiderivatives and set-valued optimization, Optimization, 58 (2009), 521-534.doi: 10.1080/02331930902928310. [12] R. Kasimbeyli, A nonlinear cone separation theorem and scalarization in nonconvex vector optimization, SIAM J. on Optimization, 20 (2009), 1591-1619. ISSN 1052-6234.doi: 10.1137/070694089. [13] R. Kasimbeyli and M. Mammadov, On weak subdifferentials, directional derivatives, and radial epiderivatives for nonconvex functions, SIAM Journal on Optimization, 20 (2009), 841-855.doi: 10.1137/080738106. [14] G. Ozturk, A New Mathematical Programming Approach to Solve Classification Problems, PhD thesis, Eskisehir Osmangazi University, Institute of Scince, 6 2007. (in Turkish). [15] R. Rosenthal, GAMS: A User's Guide, GAMS Development Corporation, Washington, DC, 2013. URL http://www.gams.com/dd/docs/bigdocs/GAMSUsersGuide.pdf. [16] K. Schittkowski, Optimal parameter selection in support vector machines, Journal of Industrial and Management Optimization, 1 (2005), 465-476.doi: 10.3934/jimo.2005.1.465.